Abstract :

Counterfeit Currency Poses A Significant Threat To Economic Stability And Financial Systems Worldwide. With The Advancement Of Printing Technologies, Counterfeiters Have Become Increasingly Capable Of Producing High-quality Fake Notes That Are Difficult To Distinguish From Genuine Ones Through Manual Inspection. This Necessitates The Development Of Automated And Intelligent Systems Capable Of Detecting Counterfeit Currency Accurately And Efficiently. The Proposed System Presents An Image-based Fake Currency Detection Approach Using Computer Vision Techniques And Machine Learning-inspired Feature Extraction. The System Utilizes OpenCV-based Image Processing Techniques To Analyze Currency Notes Uploaded By The User Through A Graphical User Interface (GUI) Built Using Tkinter. The Uploaded Image Is First Converted To Grayscale And Resized For Standardization. Edge Detection Is Performed Using The Canny Edge Detection Algorithm To Identify Structural Boundaries And Fine Details In The Currency Note. Additionally, ORB (Oriented FAST And Rotated BRIEF) Feature Extraction Is Employed To Detect Key Points And Descriptors That Represent Unique Visual Patterns Of The Note. The Number Of Detected Key Points Plays A Crucial Role In Determining The Authenticity Of The Currency. Genuine Notes Typically Contain Intricate Patterns, Textures, And Micro-details, Resulting In A Higher Number Of Detectable Key Points. In Contrast, Counterfeit Notes Often Lack Such Complexity, Leading To Fewer Key Points. A Threshold-based Classification Mechanism Is Implemented, Where The Note Is Classified As Genuine Or Fake Depending On Whether The Number Of Key Points Exceeds A Predefined Threshold.The System Provides Visual Feedback By Displaying The Uploaded Image Along With Edge-detected And Key Pointhighlighted Images. The Final Classification Result Is Presented Clearly To The User. This Approach Offers A Simple Yet Effective Solution Without Requiring Complex Deep Learning Models, Making It Computationally Efficient And Suitable For Real-time Applications. Although The System Demonstrates Promising Results, It Has Limitations Such As Dependency On Image Quality, Lighting Conditions, And Threshold Tuning. Future Enhancements May Include Integrating Deep Learning Techniques Such As Convolution Neural Networks (CNNs) For Improved Accuracy And Robustness. Overall, The Proposed System Contributes To The Development Of Low-cost And Accessible Counterfeit Detection Solutions, Especially Useful For Small Businesses And Individuals.

Published:

07-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1512-1521

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite